© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117477
    Prev
    Next
    INDEX
    Explanations

    code statements and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interconnect
    -0.77
    icach
    -0.75
     Duan
    -0.74
    isConnected
    -0.72
    onnect
    -0.71
     internation
    -0.70
    tahun
    -0.69
    ந்த
    -0.68
     tež
    -0.68
     conces
    -0.67
    POSITIVE LOGITS
    Abo
    0.74
    layered
    0.71
    hov
    0.66
    出し
    0.66
    dokument
    0.65
    cellor
    0.64
    нциклопедия
    0.63
     Dokument
    0.63
    vig
    0.62
     lágrimas
    0.62
    Activations Density 0.075%

    No Known Activations